CEGE0042 Assignment - data prep

Document description:

This notebook contains code to process raw data provided for CEGE0042 final assignment. It covers:

1. Project set up

2. Area selection (Islington)

3. Data sub-selection for further analysis

1. Project set up:

#Packages
library(sf)

Linking to GEOS 3.5.1, GDAL 2.2.2, PROJ 4.9.2

library(sp)
library(tmap)

Registered S3 methods overwritten by 'htmltools':
  method               from         
  print.html           tools:rstudio
  print.shiny.tag      tools:rstudio
  print.shiny.tag.list tools:rstudio
Registered S3 method overwritten by 'htmlwidgets':
  method           from         
  print.htmlwidget tools:rstudio
replacing previous import ‘sf::st_make_valid’ by ‘lwgeom::st_make_valid’ when loading ‘tmap’

#Working directory definition
#getwd()

#Load data
cege_data <- "./0_source_data/UJTWorkSpace.RData"
load(cege_data)

2. Area selection (Islington)

Flag links with data

#In UJT there are 256 link ids with data
all_UJT_links <- colnames(UJT)
length(all_UJT_links)

[1] 256

#In our shape file, there are 1402 link ids
length(LCAPShp$LCAP_ID)

[1] 1402

#Flag which links in shape file we have data for
LCAPShp$HaveDataFlag <- 0

counter <- 0
for (master_link_value in LCAPShp$LCAP_ID) {
  counter <- counter + 1
  
  if (master_link_value %in% all_UJT_links) {
    LCAPShp$HaveDataFlag[counter] <- 1
  }
  else{
    LCAPShp$HaveDataFlag[counter] <- 0
  }
  
}

#Check that sum is equal to all links we have data for
sum(LCAPShp$HaveDataFlag)

[1] 256

Sub-select links (visualise data availablity)

# Link shp file to to sf object
LCAPShp_sf <- st_as_sf(LCAPShp)

# Visualise field to show links with speed data
#plot(LCAPShp_sf["HaveDataFlag"])

# Load reference shape file for London Borough
# read in polygon shp and set crs to match 
LondonBor <- st_read('./1_shape_files/shapefiles/London_Borough_Excluding_MHW.shp') %>%
  st_transform(LondonBor, crs = st_crs(LCAPShp_sf))

Reading layer `London_Borough_Excluding_MHW' from data source `/cloud/project/1_shape_files/shapefiles/London_Borough_Excluding_MHW.shp' using driver `ESRI Shapefile'
Simple feature collection with 33 features and 7 fields
geometry type:  MULTIPOLYGON
dimension:      XY
bbox:           xmin: 503568.2 ymin: 155850.8 xmax: 561957.5 ymax: 200933.9
proj4string:    +proj=tmerc +lat_0=49 +lon_0=-2 +k=0.999601272 +x_0=400000 +y_0=-100000 +datum=OSGB36 +units=m +no_defs 

# for interactive viewing 
tmap_mode("view")

tmap mode set to interactive viewing

# layer the boroughs, all links, and selected links 
tm_shape(LondonBor)+
  tm_polygons(col='white')+
  tm_shape(LCAPShp_sf)+
  tm_lines(col='lightgreen')+
  tm_shape(LCAPShp_sf["LCAP_ID"])+
  tm_lines(col = "LCAP_ID")

#LCAP_ID
#HaveDataFlag

Select area(s)

# get all links that are totally within a given borough
LCAPShp_sf_sub <- LCAPShp_sf[st_within(LCAPShp_sf, 
                              LondonBor[LondonBor$NAME == "Islington",], 
                              sparse = FALSE),]

although coordinates are longitude/latitude, st_within assumes that they are planar

# check number of links in the subset
link_list <- LCAPShp_sf_sub$LCAP_ID

length(link_list)

[1] 31

# export list of links
print(link_list)

 [1] 2464  418 1807 1810 1607 1321 1632 1444 1445 1626 1426 1430 2054 2055 2420 2421 2422 2423
[19] 2058 2061 2126 2425 2428  448  450  583  481  589 2429  650  692

write.csv(x = link_list,"./2_data_split/selected_links.csv")

visualise links

# plot to take a look
plot(LCAPShp_sf_sub)

# for interactive viewing 
tmap_mode("view")

# layer the boroughs, all links, and selected links 
tm_shape(LondonBor)+
  tm_polygons(col='white')+
  tm_shape(LCAPShp_sf)+
  tm_lines(col='lightgreen')+
  tm_shape(LCAPShp_sf_sub)+
  tm_lines(col='red')

3. Data sub-selection for further analysis

3.1 UJT table

UJT table - each link (column) across time (row)

# Export all source data into python friendly .csv files

# Take selected links and export selections of source data

# select relevant columns

counter = 0
link_list_string <- c()

for (entry in link_list) {
  #print(entry)
  counter <- counter + 1
  temp_string <- toString(entry)
  link_list_string[[counter]] <- temp_string
}
link_list
link_list_string

sort(colnames(UJT))

UJT[,c("2464")]